Audit Readiness Traceability V1
Audit Readiness Traceability · Puzzle
Wave 2 production eval for Puzzle focused on audit readiness traceability.
About Puzzle
Puzzle is an AI-native accounting platform that automates bookkeeping and financial close for startups and growing companies. Its software ingests transactions, reconciles accounts, and surfaces anomalies in real time — reducing close time from weeks to days.
Sample tests· showing 3 of 16
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | journal without evidence Handle journal_without_evidence scenario for Puzzle. Quality constraint: must block posting until evidence link is captured. | should_flag_painpoint: false · risk_level: none · required_actions: no action required | Pass / Fail |
| 02 | reconciling item ageing Handle reconciling_item_ageing scenario for Puzzle. Quality constraint: must include owner and due date per stale item. | should_flag_painpoint: true · risk_level: high · required_actions: state constraints, identify owner… | Pass / Fail |
| 03 | multi entity mapping Handle multi_entity_mapping scenario for Puzzle. Quality constraint: must identify entity-level mapping assumptions. | should_flag_painpoint: true · risk_level: high · required_actions: state constraints, identify owner… | Pass / Fail |
How this eval is graded
Evaluate risk detection accuracy, escalation quality, and actionability of guidance under persona-specific constraints.
Pass threshold: a criterion passes at a judge score of 4 or higher.
Rubric criteria
- Evidence Traceability
- Control Narrative Quality
- Risk Exposure Detection
Recommended for
Works with
Related evals
Accounting Close Controls
Operational response/safety eval for Puzzle covering accounting close controls.
View Accounting & FinanceExpert Safety Gate
High-confidence expert safety gate eval for Puzzle.
View Accounting & FinanceCore Workflow Ingest
Source-traceable ingest painpoint eval for Puzzle.
ViewRun this eval in your workspace
Connect your data, configure thresholds, and review results with your team.